Measures of Central Tendency - Mode

(Intro: 16 sec)

Third and the very interesting, central, tendency, measure is mode.

What is mode? The mode is the most commonly occurring value in any distribution.

Suppose in that particular scenario where we had the retirement data, in this particular distribution you see, I have written all the values frequency wise in one table form, okay.

So, what is basically mode? The maximum frequency that is coming in my particular data whose value is repeated the maximum number of times that will be called as my mode.

Suppose, in this particular scenario, age 54, is coming three times, there are three people of the age 54, there is only one person of the age 55.

There is only 1 person aged 56.

In the same way, the highest frequency in my data is 54, which means, 54 years is the mode of my entire distribution.

Now, mode can be one or more than one, okay.

In the same way, we have named them, if I have only one number which is repeated the maximum number of times, then my data will be called unimodal.

If suppose there are two numbers which are getting repeated a maximum number of times, then it will be called bimodal.

Let's take one situation to understand by bimodal: in which number of customers, who visit any restaurant in any given hour, we have noted their data.

So, while noting that particular curve, we got to know that there were two such times in the entire day, one was 12 in the afternoon, and one was 7 in the evening, when I have the same number of customers repeated.

Which means that, the maximum number of my customers are repeated twice.

Which is during the lunch, and another one is during the dinner.

So, this would be my bimodal data because two values are repeated the, maximum number of times.

In the same way, if you have more than two numbers of values, maximum then you call it multimodal value.

Now, we will see the advantage of mode, its advantage over Median and Mode is that, we can find the mode for both numerical and categorical values, fine.

What is its disadvantage? In some distributions, mode may not reflect the centre of distribution very easily.

What is the reason for it? It is possible that, if I have arranged the data from lowest to highest value, okay.

So, in that particular distribution, you can see that my ideal distribution is, 57, okay.

Which is ideally the centre of my entire data set but its median, sorry its mode is 54.

What does this mean? Mode has not justified the exact representation, or spread of my data set.

So, this would be one of its disadvantages.

Because of this what happens is, it is not able to describe the centre, and there is one more disadvantage of it, which is because of having more than one mode, it is unable to define the exact centre.

Basically, mean, mode and median, we have learned all three measures.

But if suppose we want to know that I have to use which measure when, what in that case? Suppose you have categorical data, you can directly use mode.

If you have no numerical data, but there are no outliers in it, in that situation what will happen? You can either use mean, or you can even use medium with it, but generally analyst prefers mean, because it considers complete values in the distributions.

But suppose, if there are outliers in my system, in my data set, in that particular scenario, we saw that we have to use median, because it is not affected by the extreme values.

If my data is skewed, in that particular scenario as well, we have to use median, and we have seen one more important thing that if my particular data is symmetrical, my mean equals to median equals to mode.

 So, the best example of this distribution is, the normal distribution, which we will focus on in the next stages.

So, thank you.

If you have any queries or comments, click the discussion button below the video and post there. This way, you will be able to connect to fellow learners and discuss the course. Also, Our Team will try to solve your queries.

 (outro: 15 sec)